This thesis dissertation proposes, as a first step, a detailed introduction to the automatic speech recognition with missing data supported by many bibliographic references. It is shown that the estimation of masks is a crucial step. Indeed, the quality of the estimated masks determines the performance of the recognition system. Improving the reliability of masks is thus an important issue. In a second step, new investigations in the field of Bayesian missing data mask estimation are presented. I propose first new mask models to model dependencies between the masks of different coefficients of a signal. These models are evaluated and compared to a reference model. The results are presented in terms of error of masks, as well as recognition ...
The application of Missing Data Theory (MDT) has shown to improve the robustness of automatic speech...
this paper we present a mask-estimation technique that uses a Bayesian classification strategy to de...
Additive noise has long been an issue for robust automatic speech recognition (ASR) systems. One app...
Ce mémoire propose, dans un premier temps, une introduction détaillée de la reconnaissance automatiq...
Ce mémoire propose, dans un premier temps, une introduction détaillée de la reconnaissance automatiq...
Missing data recognition has been developped in order to increase noise robustness in automatic spee...
International audienceAutomatic speech recognition (ASR) has reached a very high level of performanc...
This paper addresses the problem of spectrographic mask estimation in the context of missing data re...
Missing feature methods of noise compensation for speech recognition operate by removing components ...
Missing feature methods of noise compensation for speech recognition operate by first identifying co...
International audienceAutomatic speech recognition (ASR) has reached very high levels of performance...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...
Texte intégral accessible uniquement aux membres de l'Université de LorraineIn this thesis we focus ...
Most automatic speech recognisers perform poorly when the training and testing conditions are not ma...
Missing data theory (MDT) has been applied to handle the problem of noise-robust speech recognition....
The application of Missing Data Theory (MDT) has shown to improve the robustness of automatic speech...
this paper we present a mask-estimation technique that uses a Bayesian classification strategy to de...
Additive noise has long been an issue for robust automatic speech recognition (ASR) systems. One app...
Ce mémoire propose, dans un premier temps, une introduction détaillée de la reconnaissance automatiq...
Ce mémoire propose, dans un premier temps, une introduction détaillée de la reconnaissance automatiq...
Missing data recognition has been developped in order to increase noise robustness in automatic spee...
International audienceAutomatic speech recognition (ASR) has reached a very high level of performanc...
This paper addresses the problem of spectrographic mask estimation in the context of missing data re...
Missing feature methods of noise compensation for speech recognition operate by removing components ...
Missing feature methods of noise compensation for speech recognition operate by first identifying co...
International audienceAutomatic speech recognition (ASR) has reached very high levels of performance...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...
Texte intégral accessible uniquement aux membres de l'Université de LorraineIn this thesis we focus ...
Most automatic speech recognisers perform poorly when the training and testing conditions are not ma...
Missing data theory (MDT) has been applied to handle the problem of noise-robust speech recognition....
The application of Missing Data Theory (MDT) has shown to improve the robustness of automatic speech...
this paper we present a mask-estimation technique that uses a Bayesian classification strategy to de...
Additive noise has long been an issue for robust automatic speech recognition (ASR) systems. One app...